Barchart水平使用matplotlib

Question

我有数据avito_trend.csv的文件，我想打印

的条形图

void dragMouse(GLint x, GLint y) {

    x = setX(x);
    y = setY(y);
    glMatrixMode(GL_PROJECTION);

    if (mouseMode == 2) {   
        printf("드래그로 도형을 옮깁니다.\n");
        glPushMatrix();
        glTranslatef((mouseX - x), (mouse - y), 0.0);
        glutPostRedisplay();
        glPopMatrix();
    }
    else if (mouseMode == 3) {
        angle += -(x - mouseX)*10.0 / 3.14;
        glRotatef(angle, 0.0, 0.0, 1.0);
    }
    else if (mouseMode == 4) {
        scale *= (1.0 + (y - mouseY) / 100.0);
        glScalef(scale, scale, 0.0);
    }
    glutPostRedisplay();
}

我使用import pandas as pd import itertools df = pd.read_csv("avito_trend.csv", parse_dates=[2]) def f(df): dfs = [] for x in [list(x) for x in itertools.combinations(df['address'].unique(), 2)]: c1 = df.loc[df['address'].isin([x[0]]), 'ID'] c2 = df.loc[df['address'].isin([x[1]]), 'ID'] c = pd.Series(list(set(c1).intersection(set(c2)))) dfs.append(pd.DataFrame({'a':len(c), 'b':' and '.join(x)}, index=[0])) return pd.concat(dfs) result = df.groupby([df['used_at'].dt.year]).apply(f).reset_index(drop=True, level=1).reset_index() print result used_at a b 0 2014 1364 avito.ru and e1.ru 1 2014 1716 avito.ru and drom.ru 2 2014 1602 avito.ru and auto.ru 3 2014 299 avito.ru and avtomarket.ru 4 2014 579 avito.ru and am.ru 5 2014 602 avito.ru and irr.ru/cars 6 2014 424 avito.ru and cars.mail.ru/sale 7 2014 634 e1.ru and drom.ru 8 2014 475 e1.ru and auto.ru 9 2014 139 e1.ru and avtomarket.ru 10 2014 224 e1.ru and am.ru 11 2014 235 e1.ru and irr.ru/cars 12 2014 154 e1.ru and cars.mail.ru/sale 13 2014 874 drom.ru and auto.ru 14 2014 247 drom.ru and avtomarket.ru 15 2014 394 drom.ru and am.ru 16 2014 423 drom.ru and irr.ru/cars 17 2014 292 drom.ru and cars.mail.ru/sale 18 2014 243 auto.ru and avtomarket.ru 19 2014 408 auto.ru and am.ru 20 2014 409 auto.ru and irr.ru/cars 21 2014 330 auto.ru and cars.mail.ru/sale 22 2014 133 avtomarket.ru and am.ru 23 2014 139 avtomarket.ru and irr.ru/cars 24 2014 105 avtomarket.ru and cars.mail.ru/sale 25 2014 223 am.ru and irr.ru/cars 26 2014 166 am.ru and cars.mail.ru/sale 27 2014 197 irr.ru/cars and cars.mail.ru/sale 28 2015 1153 avito.ru and e1.ru 29 2015 1473 avito.ru and auto.ru 30 2015 1491 avito.ru and drom.ru 31 2015 403 avito.ru and irr.ru/cars 32 2015 205 avito.ru and avtomarket.ru 33 2015 256 avito.ru and cars.mail.ru/sale 34 2015 262 avito.ru and am.ru 35 2015 451 e1.ru and auto.ru 36 2015 539 e1.ru and drom.ru 37 2015 148 e1.ru and irr.ru/cars 38 2015 105 e1.ru and avtomarket.ru 39 2015 105 e1.ru and cars.mail.ru/sale 40 2015 99 e1.ru and am.ru 41 2015 799 auto.ru and drom.ru 42 2015 288 auto.ru and irr.ru/cars 43 2015 162 auto.ru and avtomarket.ru 44 2015 195 auto.ru and cars.mail.ru/sale 45 2015 224 auto.ru and am.ru 46 2015 277 drom.ru and irr.ru/cars 47 2015 175 drom.ru and avtomarket.ru 48 2015 189 drom.ru and cars.mail.ru/sale 49 2015 187 drom.ru and am.ru 50 2015 73 irr.ru/cars and avtomarket.ru 51 2015 94 irr.ru/cars and cars.mail.ru/sale 52 2015 102 irr.ru/cars and am.ru 53 2015 48 avtomarket.ru and cars.mail.ru/sale 54 2015 72 avtomarket.ru and am.ru 55 2015 73 cars.mail.ru/sale and am.ru 我希望得到this graph之类的东西。 我该怎么做？ 我需要2014年和2015年的意义在其他一对网站的一个方面。 相反，我需要列ax = result.plot(width=0.5, kind='barh', stacked=True)

的意思

Answer 1

正如@ user308827已经说过的那样，我也会使用seaborn，但我会采用不同的方式：

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

pd.set_option('display.expand_frame_repr', False)

cols = ['ID', 'address', 'used_at']
df = pd.read_csv(r'D:\data\gDrive\data\.stack.overflow\data\avito_trend.csv.gz',
                 parse_dates=['used_at'], usecols=cols)

df.sort_values(['ID','used_at','address'], inplace=True)

df['prev_address'] = df['address'].shift()
df['time_diff'] = df['used_at'] - df['used_at'].shift()

df = df[df['address'] != df['prev_address']]
df = df[df['time_diff'] <= pd.Timedelta('10min')]


tmp = df[['ID','address','prev_address']] \
      .groupby(['address','prev_address', df.used_at.dt.year]) \
      .count() \
      .reset_index()

# remove `df` from memory
del df

tmp['visit_from'] = tmp['prev_address'] + ' -> ' + tmp['address']

# keep only 'interesting' columns
tmp = tmp[['visit_from','used_at','ID']]
tmp.columns = ['visit_from','year','visits']

# save temporary groupped CSV file
#fn = r'D:\data\gDrive\data\.stack.overflow\data\avito_grp.csv'
#tmp.to_csv(fn, index=False)

# show all
#df = tmp

# show only those sites with visits >= 100 (within both years)
df = tmp[tmp.groupby('visit_from')['visits'].transform('sum') >= 100].reset_index()

# prepare sorted index
idx = df.groupby('visit_from')['visits'].transform('sum').sort_values(ascending=False).index

# 'apply' index
df = df.reindex(idx)

# add 'total' column (sum of visits for all years)
#df['total'] = df.groupby('visit_from')['visits'].transform('sum')

################################################
#
# SeaBorn plotting
#
sns.set(style="darkgrid")
sns.set_color_codes("pastel")

f, ax = plt.subplots(figsize=(16, 12))
ax = sns.barplot(x='visits', y='visit_from', hue='year', data=df, saturation=0.8)
plt.xlabel('Visits')

# add annotations
[ax.text(p.get_width() + 3, p.get_y() + p.get_height(),
         int(p.get_width()), fontsize=8)
 for p in ax.patches]


plt.show()

PS对你有意思的部分以SeaBorn plotting评论

开头

Answer 2

尝试seaborn

来自https://stanford.edu/~mwaskom/software/seaborn/generated/seaborn.barplot.html

import seaborn as sns
sns.set_style("whitegrid")
tips = sns.load_dataset("tips")
ax = sns.barplot(x="day", y="total_bill", data=tips)

对于堆积条形图： https://gist.github.com/randyzwitch/b71d47e0d380a1a6bef9